Zed now predicts your next edit with Zeta, our new open model

Re:Zed now predicts your next edit with Zeta, our new open m... by levzzz on Friday February 14, 2025 @06:41AM (#43047366)

yeah, i'd like to be able to run it locally. it should fit well onto my 12gb gpu

[ Parent | on HN ]

Re:Zed now predicts your next edit with Zeta, our new open m... by mbitsnbites on Friday February 14, 2025 @08:12AM (#43047955)

The model is based on Qwen2.5-Coder-7b it seems. I currently run some quantized variant of Qwen2.5-Coder-7b locally with llama.cpp and it fits nicely in the 8GB VRAM of my Radeon 7600 (with excellent performance BTW), so it looks like it should be perfectly possible.

I would also only use Zeta locally.

[ Parent | on HN ]

Re:Zed now predicts your next edit with Zeta, our new open m... by jbk on Friday February 14, 2025 @08:27AM (#43048056)

Are you happy with the speed with your 8GB GPU?

[ Parent | on HN ]